Using random forest based outlier detection and imputation to clean a #kaggle dataset. (Specifically the outForest and isoforest #rstats packages 📦, which implement different kinds of random forest methods.)

Achieved only a marginal gain in out-of-sample accuracy with a random forest model, but the real treasure was the methods I learned along the way. 💎

🔗 https://tylerburleigh.com/blog/2023/09/08/

初のKaggleで銅メダル、初のSIGNATEで金メダルを獲ったおはなし
https://qiita.com/katoro13/items/aa63f9eb77c800a05b5f?utm_campaign=popular_items&utm_medium=feed&utm_source=popular_items
#qiita #初心者 #機械学習 #Kaggle #SIGNATE

【データ分析】5か月でゴールドをとれた私文の僕が「やってよかったこと」
https://qiita.com/hexagon0423/items/d6f4453819d854c63d17?utm_campaign=popular_items&utm_medium=feed&utm_source=popular_items
#qiita #機械学習 #データ分析 #データサイエンス #Kaggle #SIGNATE

I am letting myself get unreasonably nerd-sniped today trying to get higher on the leaderboard for this Kaggle competition:
https://www.kaggle.com/competitions/playground-series-s3e20/overview

It's not a horrible way to keep my data nerditude / ML skills existent, if I could just do so without the layer of Proving Myself Good Enough At This lurking in the background.

But also, winners get swag. I love winning swag, not gonna lie.
#math #ML #kaggle #datascience

Kaggle is the largest AI/ML Community

https://www.kaggle.com

#kaggle #community #AI #ML

I really love #Kaggle ! When I started my AI degree I also started scouting the web for good learning content that is more than "just" youtube tutorials. For me Kaggle is really ticking all boxes. Good learning material, tutorials based on readily available notebooks, lots of datasets available for experiments, an online forum to ask questions in and a badging system that shows your progress...

The U.S. House has a bipartisan food recovery caucus, members of which recently introduced a bill to standardize food date label language to reduce #waste: https://newhouse.house.gov/media-center/press-releases/newhouse-reintroduces-bicameral-bill-standardize-food-date-labels-cut. A few years ago I led a small research project to collect data on labeling present on food that stores in downtown #brooklyn had trashed, and you can find some community analysis on #kaggle here: https://www.kaggle.com/datasets/ursulakaczmarek/brooklyn-food-waste/code #python

#kaggle #gpu #LeNet #training

OpenMMLabの始め方@ SUMMER 2023
https://qiita.com/fam_taro/items/7f028dfeae2a79a10fe1?utm_campaign=popular_items&utm_medium=feed&utm_source=popular_items
#qiita #Python #機械学習 #Kaggle #PyTorch #OpenMMLab

Is there an updated version of the #Titanic survivors challenge on #Kaggle already?

Matching mentors & mentees is a good thing. But I assume a for-profit like #kaggle should provide an incentive beyond "swags" to mentors in the KaggleX BIPOC Mentorship Program. I'd be pleased to participate one day but if I'm donating my time, I'd donate it to a non-profit!

I just uploaded the final data backup from my Popular Twitter bots project: https://www.kaggle.com/datasets/fourtonfish/popular-twitter-bots

It looks like it lost access to Twitter's API on April 27. It was fun while it lasted!

https://twitterbots.glitch.me

#dataviz #dataset #kaggle #twitter #TwitterBots #TwitterPI

I just uploaded the final data backup from my Popular Twitter bots project: https://www.kaggle.com/datasets/fourtonfish/popular-twitter-bots

It looks like it lost access to Twitter's API on April 27. It was fun while it lasted!

https://twitterbots.glitch.me

#dataviz #dataset #kaggle #twitter #TwitterBots #TwitterPI

We just got to 100 teams in the #CAFA5 challenge on Kaggle

Join the fun, predict protein function, advance science and perhaps win a prize!

#Bioinformatics
#ProteinFunctionPrediction
#MachineLearning
#Kaggle

https://www.kaggle.com/competitions/cafa-5-protein-function-prediction/

#CAFA5 The 5th round of the Critical Assessment of protein Function Annotation is live on #kaggle and we have $$ prizes! There are many proteins in the databases for which the sequence is known, but the function is not. A major challenge in bioinformatics is to predict the function of a protein from its sequence or structure. At the same time, how can we judge how well these function prediction algorithms are performing?
#machinelearning #bioinformatics

https://www.kaggle.com/competitions/cafa-5-protein-function-prediction

I did not realize you can post up to 100GB of data to #Kaggle and they provide access to computational resources and #Jupyter notebooks.

We're thinking about automatically posting all our #PUDL data there, and maybe running community competitions to help solve entity matching, anomaly detection, and imputation problems. Is there any downside to doing this?

#OpenData #MachineLearning #DataScience #EnergyTransition #EnergyTwitter #EnergyMastodon

https://www.kaggle.com/datasets/zaneselvans/catalyst-cooperative-pudl

Here's a chance to use #MachineLearning for something useful. Kaggle is running a competition to develop an automatic solution that will extract data represented by four types of charts commonly found in STEM textbooks to help students with a learning, physical, or visual disability.

And you can win a portion of the $50,000 total in awards.

https://www.kaggle.com/competitions/benetech-making-graphs-accessible

#data #DataScience #DataVisualization #accessibility #a11y #kaggle #competition #hackathon #learning #stem

I upload a dataset to #Kaggle this about dairy production in Chile. Here is the link: https://www.kaggle.com/datasets/indynavarrovidal/chilean-dairy-production

My jet lag is getting better little by little. I cartooned my wedding photos for fun yesterday with Python. I realized that there are so many things I can do with #Kaggle notebooks. I need to explore more of the potential.

I have been playing a Japanese Baseball game on PS5, and also Netflix has a lot of dramas by TBS (Tokyo Broadcasting System) now. Kudo Kankuro is my must-go screenwriter. I watched IWGP already and there are two more drama series by him.

Join our #Kaggle competition to help improve #MachineLearning for #DeepSea images.

This competition is all about out-of-sample detection and could help scientists discover new animals and improve ecosystem management practices.

https://www.kaggle.com/competitions/fathomnet-out-of-sample-detection/overview

#FathomNet